Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +82 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- quantize_config.json +61 -0
- special_tokens_map.json +4 -0
- tokenizer_config.json +30 -0
- vocab.json +74 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 72
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/mms-tts-hin",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"architectures": [
|
5 |
+
"VitsModel"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"depth_separable_channels": 2,
|
9 |
+
"depth_separable_num_layers": 3,
|
10 |
+
"duration_predictor_dropout": 0.5,
|
11 |
+
"duration_predictor_filter_channels": 256,
|
12 |
+
"duration_predictor_flow_bins": 10,
|
13 |
+
"duration_predictor_kernel_size": 3,
|
14 |
+
"duration_predictor_num_flows": 4,
|
15 |
+
"duration_predictor_tail_bound": 5.0,
|
16 |
+
"ffn_dim": 768,
|
17 |
+
"ffn_kernel_size": 3,
|
18 |
+
"flow_size": 192,
|
19 |
+
"hidden_act": "relu",
|
20 |
+
"hidden_dropout": 0.1,
|
21 |
+
"hidden_size": 192,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"layerdrop": 0.1,
|
25 |
+
"leaky_relu_slope": 0.1,
|
26 |
+
"model_type": "vits",
|
27 |
+
"noise_scale": 0.667,
|
28 |
+
"noise_scale_duration": 0.8,
|
29 |
+
"num_attention_heads": 2,
|
30 |
+
"num_hidden_layers": 6,
|
31 |
+
"num_speakers": 1,
|
32 |
+
"posterior_encoder_num_wavenet_layers": 16,
|
33 |
+
"prior_encoder_num_flows": 4,
|
34 |
+
"prior_encoder_num_wavenet_layers": 4,
|
35 |
+
"resblock_dilation_sizes": [
|
36 |
+
[
|
37 |
+
1,
|
38 |
+
3,
|
39 |
+
5
|
40 |
+
],
|
41 |
+
[
|
42 |
+
1,
|
43 |
+
3,
|
44 |
+
5
|
45 |
+
],
|
46 |
+
[
|
47 |
+
1,
|
48 |
+
3,
|
49 |
+
5
|
50 |
+
]
|
51 |
+
],
|
52 |
+
"resblock_kernel_sizes": [
|
53 |
+
3,
|
54 |
+
7,
|
55 |
+
11
|
56 |
+
],
|
57 |
+
"sampling_rate": 16000,
|
58 |
+
"speaker_embedding_size": 0,
|
59 |
+
"speaking_rate": 1.0,
|
60 |
+
"spectrogram_bins": 513,
|
61 |
+
"transformers_version": "4.37.0.dev0",
|
62 |
+
"upsample_initial_channel": 512,
|
63 |
+
"upsample_kernel_sizes": [
|
64 |
+
16,
|
65 |
+
16,
|
66 |
+
4,
|
67 |
+
4
|
68 |
+
],
|
69 |
+
"upsample_rates": [
|
70 |
+
8,
|
71 |
+
8,
|
72 |
+
2,
|
73 |
+
2
|
74 |
+
],
|
75 |
+
"use_bias": true,
|
76 |
+
"use_stochastic_duration_prediction": true,
|
77 |
+
"vocab_size": 72,
|
78 |
+
"wavenet_dilation_rate": 1,
|
79 |
+
"wavenet_dropout": 0.0,
|
80 |
+
"wavenet_kernel_size": 5,
|
81 |
+
"window_size": 4
|
82 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb1e76988b30d3617b8a1480941e3a57f1bdb474447cee88e3666de1c1332821
|
3 |
+
size 114284918
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac30287f8b50c9eecb3959cea623ebc4b82bff4dcbb9b63eebc100034be065d8
|
3 |
+
size 38368171
|
quantize_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Pow",
|
8 |
+
"Unsqueeze",
|
9 |
+
"Sub",
|
10 |
+
"Not",
|
11 |
+
"Clip",
|
12 |
+
"Mul",
|
13 |
+
"Sigmoid",
|
14 |
+
"LeakyRelu",
|
15 |
+
"ReduceMean",
|
16 |
+
"ScatterND",
|
17 |
+
"Greater",
|
18 |
+
"Less",
|
19 |
+
"Range",
|
20 |
+
"Squeeze",
|
21 |
+
"Shape",
|
22 |
+
"Conv",
|
23 |
+
"ConstantOfShape",
|
24 |
+
"NonZero",
|
25 |
+
"Transpose",
|
26 |
+
"Gather",
|
27 |
+
"Slice",
|
28 |
+
"CumSum",
|
29 |
+
"ConvTranspose",
|
30 |
+
"Where",
|
31 |
+
"Expand",
|
32 |
+
"Softplus",
|
33 |
+
"MatMul",
|
34 |
+
"GatherND",
|
35 |
+
"Add",
|
36 |
+
"Sqrt",
|
37 |
+
"Concat",
|
38 |
+
"Erf",
|
39 |
+
"ReduceMax",
|
40 |
+
"GatherElements",
|
41 |
+
"Constant",
|
42 |
+
"Split",
|
43 |
+
"Neg",
|
44 |
+
"Equal",
|
45 |
+
"Softmax",
|
46 |
+
"Relu",
|
47 |
+
"And",
|
48 |
+
"ReduceSum",
|
49 |
+
"Exp",
|
50 |
+
"Reshape",
|
51 |
+
"Pad",
|
52 |
+
"Tanh",
|
53 |
+
"Div",
|
54 |
+
"Cast",
|
55 |
+
"Ceil",
|
56 |
+
"RandomNormalLike"
|
57 |
+
],
|
58 |
+
"weight_type": "QUInt8"
|
59 |
+
}
|
60 |
+
}
|
61 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "फ",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_blank": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "फ",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"72": {
|
13 |
+
"content": "<unk>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"clean_up_tokenization_spaces": true,
|
22 |
+
"is_uroman": false,
|
23 |
+
"language": "hin",
|
24 |
+
"model_max_length": 1000000000000000019884624838656,
|
25 |
+
"normalize": true,
|
26 |
+
"pad_token": "फ",
|
27 |
+
"phonemize": false,
|
28 |
+
"tokenizer_class": "VitsTokenizer",
|
29 |
+
"unk_token": "<unk>"
|
30 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 7,
|
3 |
+
"'": 44,
|
4 |
+
"-": 3,
|
5 |
+
"0": 8,
|
6 |
+
"1": 2,
|
7 |
+
"2": 18,
|
8 |
+
"3": 25,
|
9 |
+
"4": 1,
|
10 |
+
"8": 6,
|
11 |
+
"_": 33,
|
12 |
+
"`": 45,
|
13 |
+
"ँ": 16,
|
14 |
+
"ं": 30,
|
15 |
+
"ः": 35,
|
16 |
+
"अ": 4,
|
17 |
+
"आ": 55,
|
18 |
+
"इ": 5,
|
19 |
+
"ई": 34,
|
20 |
+
"उ": 32,
|
21 |
+
"ऊ": 65,
|
22 |
+
"ए": 11,
|
23 |
+
"ऐ": 12,
|
24 |
+
"ऑ": 19,
|
25 |
+
"ओ": 67,
|
26 |
+
"औ": 60,
|
27 |
+
"क": 70,
|
28 |
+
"ख": 42,
|
29 |
+
"ग": 49,
|
30 |
+
"घ": 47,
|
31 |
+
"च": 17,
|
32 |
+
"छ": 9,
|
33 |
+
"ज": 57,
|
34 |
+
"झ": 58,
|
35 |
+
"ञ": 26,
|
36 |
+
"ट": 68,
|
37 |
+
"ठ": 29,
|
38 |
+
"ड": 56,
|
39 |
+
"ढ": 50,
|
40 |
+
"ण": 43,
|
41 |
+
"त": 69,
|
42 |
+
"थ": 20,
|
43 |
+
"द": 62,
|
44 |
+
"ध": 37,
|
45 |
+
"न": 10,
|
46 |
+
"प": 48,
|
47 |
+
"फ": 0,
|
48 |
+
"ब": 41,
|
49 |
+
"भ": 21,
|
50 |
+
"म": 71,
|
51 |
+
"य": 51,
|
52 |
+
"र": 39,
|
53 |
+
"ल": 38,
|
54 |
+
"व": 46,
|
55 |
+
"श": 59,
|
56 |
+
"ष": 14,
|
57 |
+
"स": 40,
|
58 |
+
"ह": 36,
|
59 |
+
"़": 13,
|
60 |
+
"ा": 54,
|
61 |
+
"ि": 15,
|
62 |
+
"ी": 22,
|
63 |
+
"ु": 28,
|
64 |
+
"ू": 66,
|
65 |
+
"ृ": 63,
|
66 |
+
"ॅ": 24,
|
67 |
+
"े": 52,
|
68 |
+
"ै": 27,
|
69 |
+
"ॉ": 31,
|
70 |
+
"ो": 61,
|
71 |
+
"ौ": 64,
|
72 |
+
"्": 53,
|
73 |
+
"": 23
|
74 |
+
}
|